A simulation based multi-criteria scheduling approach of dual-resource constrained manufacturing systems with neural networks

Araz O. U.

18th Australian Joint Conference on Artificial Intelligence, AI 2005: Advances in Artificial Intelligence, Sydney, Australia, 5 - 09 December 2005, pp.1047-1052, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1007/11589990_138
  • City: Sydney
  • Country: Australia
  • Page Numbers: pp.1047-1052
  • Dokuz Eylül University Affiliated: Yes

Abstract

This paper presents a multicriteria DRC scheduler in order to select appropriate dispatching rules. This scheduler integrates several tools, namely; a simulation model, a backpropagation neural network (BPNN) and a Multicriteria decision aid (MCDA) method. Simulation is used to collect predefined performance measures corresponding to decision rule set and system state variables. Because of the time consuming nature of simulation, BPNN is used to obtain the performance measures for each alternative schedule. In order to compare the system performance between all alternatives, the evaluation of each alternative is performed by PROMETHEE, which is a well-known MCDA method. By means of a realistic numerical example, the proposed methodology is proved to be an effective method in a DRC manufacturing system. © Springer-Verlag Berlin Heidelberg 2005.